A method and system are provided to combine best practices with a new discovery method, incentive structure and tracking system for better results in the referral process, particularly in the domain of employment. Crowdsourcing using a tiered peer-to-peer referral incentive system that encourages higher quality inbound leads combined with data analytics and machine learning techniques of identifying high quality referrers and candidates improve success rates, and leveraging online and offline Social and Professional networks creates a frictionless user experience. tracking technologies and methods inspired by the online advertising industry across a variety of platforms (desktop/handheld/wearable devices) enable improved crowdsourcing and reward strategies.
|
13. An apparatus comprising:
one or more hardware processors; and
a non-transitory computer-readable storage medium coupled to the processor, wherein the non-transitory computer readable storage medium comprises instructions operable to cause the one or more hardware processors to:
organize in a database, company information, job information, candidate information, and tracking elements that contain information related to referral criteria;
track, in the database, a referrer quality of each candidate through a multi-dimensional analysis of each candidate's ability to serve as a referrer, the multi-dimensional analysis including, for each respective candidate, scoring the respective candidate according to a number of prior job referrals and respective outcomes of each of the prior job referrals;
calculate, based on a distance function of at least two dimensions from the database, candidate match scores;
enforce, via the database, referral criteria based on the tracking elements, receive job description data associated with a job opening;
identify a seed population of candidates from a plurality of candidates based on the job information, candidate match scores, and referrer quality data;
notify the seed population of candidates of the job opening via a plurality of trackable electronic notification messages, wherein each of the plurality of trackable electronic notification messages identifies specific candidates in the seed population of candidates and wherein each of the plurality of trackable electronic notification messages includes a tracking element incorporating a unique identifier associated with the job opening and the specific candidate, the notifying including, for each candidate from the seed population of candidates, generating a tracking pixel as the tracking element, the generating including:
forming a concatenation of an identifier of the candidate, at least a portion of the company information, and at least a portion of the job information from the database; and
assigning a referral limit to the tracking pixel, the referral limit specifying a number of modifications to the tracking pixel after which the tracking pixel is no longer eligible for modification;
form a chain of referrals, wherein the chain of referrals is formed by:
tracking forwarding of the plurality of trackable electronic notification messages from one candidate to another candidate based on the tracking element, the tracking including, for each instance of forwarding, modifying the tracking pixel to include data unique to the another candidate;
identifying referral hops based on results of the tracking of the plurality of trackable electronic notification messages, the identifying including omitting instances of forwarding that modified the tracking pixel after the tracking pixel was no longer eligible for modification; and
inferring the chain of referrals based on the identified referral hops, wherein the chain of referrals corresponds to the propagation of information regarding the job opening between candidates;
receive a job application from an end candidate in the chain of referrals wherein the job application includes a particular trackable electronic notification message of the plurality of trackable electronic notification messages;
receive a notification that the end candidate has been hired; and
cause the candidates in the chain of referrals corresponding to the hired end candidate and the particular trackable notification message to be rewarded.
1. A computer-implemented method for organizing a job referral database comprising:
organizing in a database, by a processor, company information, job information, candidate information, and tracking elements that contain information related to referral criteria;
tracking, in the database, by the processor, a referrer quality of each candidate through a multi-dimensional analysis of each candidate's ability to serve as a referrer, the multi-dimensional analysis including, for each respective candidate, scoring the respective candidate according to a number of prior job referrals and respective outcomes of each of the prior job referrals;
calculating, by the processor, based on a distance function of at least two dimensions from the database, candidate match scores;
enforcing, by the processor via the database, referral criteria based on the tracking elements, receiving job description data associated with a job opening;
identifying, by the processor from within the database, a seed population of candidates from a plurality of candidates based on the job information, candidate match scores, and referrer quality data;
notifying, by the processor, the seed population of candidates of the job opening via a plurality of trackable electronic notification messages, wherein each of the plurality of trackable electronic notification messages identify specific candidates in the seed population of candidates and wherein each of the plurality of trackable electronic notification messages includes a tracking element incorporating a unique identifier associated with the job opening and the specific candidate, the notifying including, for each candidate from the seed population of candidates, generating a tracking pixel as the tracking element, the generating including:
forming a concatenation of an identifier of the candidate, at least a portion of the company information, and at least a portion of the job information from the database; and
assigning a referral limit to the tracking pixel, the referral limit specifying a number of modifications to the tracking pixel after which the tracking pixel is no longer eligible for modification;
forming within the database a chain of referrals, by the processor, wherein the forming includes:
tracking forwarding of the plurality of trackable electronic notification messages from one candidate to another candidate based on the tracking element, the tracking including, for each instance of forwarding, modifying the tracking pixel to include data unique to the another candidate;
identifying referral hops based on results of the tracking of the plurality of trackable electronic notification messages, the identifying including omitting instances of forwarding that modified the tracking pixel after the tracking pixel was no longer eligible for modification; and
inferring the chain of referrals based on the identified referral hops, wherein the chain of referrals corresponds to the propagation of information regarding the job opening between candidates;
receiving, by the processor, a job application from an end candidate in the chain of referrals wherein the job application includes a particular trackable electronic notification message of the plurality of trackable electronic notification messages;
receiving, by the processor, a notification that the end candidate has been hired; and
causing, by the processor, rewarding of the candidates in the chain of referrals corresponding to the hired end candidate and the particular trackable electronic notification message.
2. The method of
3. The method of
4. The method of
5. The method of
6. The method of
7. The method of
8. The method of
9. The method of
10. The method of
11. The method of
12. The method of
14. The apparatus of
15. The apparatus of
forwarded to new additional candidates more frequently than a predetermined threshold number of times within a predetermined amount of time, or
forwarded to new additional candidates at a more frequent interval than a predetermined time interval.
16. The apparatus of
17. The apparatus of
18. The apparatus of
19. The method of
20. The apparatus of
|
This application claims the benefit of U.S. Provisional Pat. App. Ser. No. 61/990,817, filed on May 9, 2014, which is hereby incorporated by reference herein in its entirety.
In today's job marketplace, there are several popular ways to discover and recruit new employees—online job postings, career events, recruiting agencies, and employee referrals. There are many incentive structures used for generating inbound leads on candidates, and several processes to interview, hire and close candidates.
The present disclosure relates to a method to combine best practices from all these domains with a new discovery method, incentive structure and tracking system for better results. This includes:
The system according to embodiments of the present disclosure can have two interfaces: one with the customers (the hiring companies) and one with the users (mass market). The overall workflow is as follows:
For example, let's say Company Foo would like to reward $20,000 for the successful hire of a Software Engineer. The system identifies John Doe as the first user in the seed population. John gets notified of the job on his smartphone and decides to pass it on to Jane via SMS. Jane downloads the system app and decides to pass it on via Facebook to Janet. Janet applies for and gets the job at Company Foo. Company Foo reports this to the system and removes its job posting and reward. The system decides to reward Janet $10,000, Jane $7,000, and John $3,000 based on where they were in the chain. Janet, Jane, and John get paid through the system or by Company Foo directly. The system can provide several payment breakdown options based on the company's preferences. Some companies will opt to give a signing bonus to Janet directly in which case the system will split the reward between Jane and John, perhaps as $14,000 and $6,000 respectively.
Processing and storage module 107 interfaces with the user facing module 108 that handles the identification of high quality referrers for different jobs, distribution of job openings to mass market users 109,110,111 of the user-facing service, and disbursing payments as shown in
The client app 505 can show the user via some user interface the Job 507 which is the same information as contained Job 503, but presented in a user-friendly format.
The user-facing client app 505 can use data collected from the above-mentioned sources in combination with algorithms described in
The user 509 communicates a referral 506 back to the client app 505 through some user action where the user 509 either applies to the job themselves or refers another user candidate. The information in referral 506 along with some tracking information collected by the client app 505 is collected as a trackable referral 501 and communicated back to the system server 502.
If V1=[Google, Boston, Engineer] and V2=[Apple, Boston, Engineer], then D(V1, V2)=1,
If V2=[Apple, Boston, Engineer] and V3=[Apple, Cupertino, Engineer], then D(V2, V3)=1,
since in both these cases two vectors differ only in a single dimension; however,
If V1=[Google, Boston, Engineer] and V3=[Apple, Cupertino, Engineer], then D(V1, V3)=2,
since both company and location are different for V1 and V3. Now let us define the Match Score function M, as M(a, b)=1/(1+D(a,b)). It is easy to see that a lower distance will mean a higher match score.
A Job Feature Vector is defined as VJ a Feature Vector that is populated with the company, location, and title of the job. Let us define a User Feature Vector VU as a Feature Vector that is populated with the user's current company of employment, the user's current location, and the user's current title within that company. The Match Score for a User U with a Job J would now be M(VJ, VU).
If slightly more importance is given to the location dimension while computing the match score, the distance function D could be modified to double the differences in location when calculating distance, effectively giving weight 2 to the location dimension. Accordingly, the new Weighted Distance Function W can behave like this:
If V1=[Google, Boston, Engineer] and V3=[Apple, Boston, Engineer], then W(V1, V2)=1
If V2=[Apple, Boston, Engineer] and V3=[Apple, Cupertino, Engineer], then W(V2, V3)=2, (because the location counts for double!)
If V1=[Google, Boston, Engineer] and V3=[Apple, Cupertino, Engineer], then W(V1, V3)=3, because it's 1 for the company difference, plus 2 for the location difference
Now, defining a new Match Score M (a, b)=1/(1+W(a,b)) can enable the Match Score to take advantage of this unequal importance of dimensions.
Using a well-known technique like supervised or semi-supervised learning with Support Vector Machines (SVMs) or clustering based SVMs for unsupervised learning, the system can improve the Match Score even further using third-party data collected about existing referral based hiring in the industry, or learning from the initial users of the system and the success conditions of their referrals. The system can also use these techniques to establish correlations between all the different dimensions, and reduce the set of dimensions to the ones that really matter for success (called dimension reduction techniques in machine learning).
An example of business intelligence might be a case where a company wishes to receive a certain number of applicants in a certain amount of time. Given these constraints, the system can relax or tighten the seed population criteria 804 to produce network effects that will meet the wishes of the company. In effect, the system can “throttle” the flow of inbound applicants to the company by using different ranges or Quality and Match Scores, along with how many referrals are allowed per user per job (refer to
The company A wishes to get 8-10 candidate applications for a particular job opening from the system, within 2 days. They have specified in their request that they would prefer referrals from people within company A.
Each user is allowed to refer at most 2 other users. For simplicity, let's assume that every user that is able to, does indeed make the maximum number of allowed referrals.
Every time a user A refers another B, it takes 1 day for B to have the time to check out the referral and take some action.
There are 100 currently active users in the system, and they each have a unique quality score 1-100. User A is from the company A, has a quality score of 100 and a match score of 1. User B and C are also from the company A have a quality score of 90, 89 respectively and both have a match score of 0.5. User D has a quality score of 95, match score of 0.4, but is not from company A. All other users have a match score of 0.2 with respect to the particular job at hand.
Given these parameters of operation, if the system wants to provide the best 8-10 candidates for the company within 2 days, that means that there can be at most 2 hops in the chain until each of the candidates is found. The algorithm can be applied as follows:
If D had a match score of 0.5, D would have ranked above B and C in the quality score and also passed the match score filter, but would be discarded during the Business Intelligence filter.
Assuming that after a day of operation with the seed population of user A, B, the system observed that there have only been three referrals (as opposed to the maximum four). This would mean that in two days, the system would only be able to yield six candidates instead of the eight expected. The system could in this situation continue to relax the filter criteria to add another seed user, C, with the hope of increasing the yield to meet the company A's expectations.
The subject matter described herein can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structural means disclosed in this specification and structural equivalents thereof, or in combinations of them. The subject matter described herein can be implemented as one or more computer program products, such as one or more computer programs tangibly embodied in an information carrier (e.g., in a machine readable storage device), or embodied in a propagated signal, for execution by, or to control the operation of, data processing apparatus (e.g., a programmable processor, a computer, or multiple computers). A computer program (also known as a program, software, software application, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file. A program can be stored in a portion of a file that holds other programs or data, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communication network.
The processes and logic flows described in this specification, including the method steps of the subject matter described herein, can be performed by one or more programmable processors executing one or more computer programs to perform functions of the subject matter described herein by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus of the subject matter described herein can be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).
Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processor of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random access memory or both. The essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. Information carriers suitable for embodying computer program instructions and data include all forms of nonvolatile memory, including by way of example semiconductor memory devices, (e.g., EPROM, EEPROM, and flash memory devices); magnetic disks, (e.g., internal hard disks or removable disks); magneto optical disks; and optical disks (e.g., CD and DVD disks). The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.
To provide for interaction with a user, the subject matter described herein can be implemented on a computer having a display device, e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information to the user and a keyboard and a pointing device, (e.g., a mouse or a trackball), by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well. For example, feedback provided to the user can be any form of sensory feedback, (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user can be received in any form, including acoustic, speech, or tactile input.
The subject matter described herein can be implemented in a computing system that includes a back end component (e.g., a data server), a middleware component (e.g., an application server), or a front end component (e.g., a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the subject matter described herein), or any combination of such back end, middleware, and front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), e.g., the Internet.
It is to be understood that the disclosed subject matter is not limited in its application to the details of construction and to the arrangements of the components set forth in the following description or illustrated in the drawings. The disclosed subject matter is capable of other embodiments and of being practiced and carried out in various ways. Also, it is to be understood that the phraseology and terminology employed herein are for the purpose of description and should not be regarded as limiting.
As such, those skilled in the art will appreciate that the conception, upon which this disclosure is based, may readily be utilized as a basis for the designing of other structures, methods, and systems for carrying out the several purposes of the disclosed subject matter. It is important, therefore, that the claims be regarded as including such equivalent constructions insofar as they do not depart from the spirit and scope of the disclosed subject matter.
Although the disclosed subject matter has been described and illustrated in the foregoing exemplary embodiments, it is understood that the present disclosure has been made only by way of example, and that numerous changes in the details of implementation of the disclosed subject matter may be made without departing from the spirit and scope of the disclosed subject matter.
Patent | Priority | Assignee | Title |
Patent | Priority | Assignee | Title |
7774229, | Aug 09 1999 | STRIPE, INC | Methods of anti-spam marketing through personalized referrals and rewards |
9454577, | Oct 16 2009 | IQOR US INC | Apparatuses, methods and systems for an employee reimbursement evaluator |
20050080657, | |||
20060212476, | |||
20060224729, | |||
20070033064, | |||
20120330701, | |||
WO2013078399, |
Executed on | Assignor | Assignee | Conveyance | Frame | Reel | Doc |
Jul 07 2021 | RANADE, VINAYAK | DRAFTED, INC | ASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS | 056787 | /0262 | |
Aug 02 2021 | DRAFTED, INC | GARUDA LABS, INC | ASSIGNMENT OF ASSIGNORS INTEREST SEE DOCUMENT FOR DETAILS | 063292 | /0386 | |
Jun 12 2024 | GARUDA LABS, INC | JPMORGAN CHASE BANK, N A | SECURITY INTEREST SEE DOCUMENT FOR DETAILS | 067900 | /0719 |
Date | Maintenance Fee Events |
Date | Maintenance Schedule |
Mar 09 2024 | 4 years fee payment window open |
Sep 09 2024 | 6 months grace period start (w surcharge) |
Mar 09 2025 | patent expiry (for year 4) |
Mar 09 2027 | 2 years to revive unintentionally abandoned end. (for year 4) |
Mar 09 2028 | 8 years fee payment window open |
Sep 09 2028 | 6 months grace period start (w surcharge) |
Mar 09 2029 | patent expiry (for year 8) |
Mar 09 2031 | 2 years to revive unintentionally abandoned end. (for year 8) |
Mar 09 2032 | 12 years fee payment window open |
Sep 09 2032 | 6 months grace period start (w surcharge) |
Mar 09 2033 | patent expiry (for year 12) |
Mar 09 2035 | 2 years to revive unintentionally abandoned end. (for year 12) |